# AutoPruner: An End-to-End Trainable Filter Pruning Method for Efficient Deep Model Inference

arXiv: https://arxiv.org/abs/1805.08941 · HTML: https://mlsanity.com/paper/1805.08941/

## Key facts

- Cited by 77 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 May 2018.

## Built on by (most cited first, 30 of 77)

- [Pruning and Quantization for Deep Neural Network Acceleration: A Survey](https://mlsanity.com/paper/2101.09671/) (2021)
- [A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations](https://mlsanity.com/paper/2308.06767/) (2023)
- [CHIP: CHannel Independence-based Pruning for Compact Neural Networks](https://mlsanity.com/paper/2110.13981/) (2021)
- [Convolutional Neural Network Pruning with Structural Redundancy Reduction](https://mlsanity.com/paper/2104.03438/) (2021)
- [Lost in Pruning: The Effects of Pruning Neural Networks beyond Test Accuracy](https://mlsanity.com/paper/2103.03014/) (2021)
- [Revisiting Random Channel Pruning for Neural Network Compression](https://mlsanity.com/paper/2205.05676/) (2022)
- [The Emergence of Essential Sparsity in Large Pre-trained Models: The Weights that Matter](https://mlsanity.com/paper/2306.03805/) (2023)
- [Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decomposition](https://mlsanity.com/paper/2107.11442/) (2021)
- [Learning Best Combination for Efficient N:M Sparsity](https://mlsanity.com/paper/2206.06662/) (2022)
- [Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning](https://mlsanity.com/paper/2102.03214/) (2021)
- [GDP: Stabilized Neural Network Pruning via Gates with Differentiable Polarization](https://mlsanity.com/paper/2109.02220/) (2021)
- [Locally Free Weight Sharing for Network Width Search](https://mlsanity.com/paper/2102.05258/) (2021)
- [Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!](https://mlsanity.com/paper/2303.02141/) (2023)
- [BCNet: Searching for Network Width with Bilaterally Coupled Network](https://mlsanity.com/paper/2105.10533/) (2021)
- [Carrying out CNN Channel Pruning in a White Box](https://mlsanity.com/paper/2104.11883/) (2021)
- [Pruning Neural Networks via Coresets and Convex Geometry: Towards No Assumptions](https://mlsanity.com/paper/2209.08554/) (2022)
- [Network Pruning using Adaptive Exemplar Filters](https://mlsanity.com/paper/2101.07985/) (2021)
- [Pruning Networks with Cross-Layer Ranking & k-Reciprocal Nearest Filters](https://mlsanity.com/paper/2202.07190/) (2022)
- [ELRT: Efficient Low-Rank Training for Compact Convolutional Neural Networks](https://mlsanity.com/paper/2401.10341/) (2024)
- [Differentiable Transportation Pruning](https://mlsanity.com/paper/2307.08483/) (2023)
- [Manipulating Identical Filter Redundancy for Efficient Pruning on Deep and Complicated CNN](https://mlsanity.com/paper/2107.14444/) (2021)
- [Performance-aware Approximation of Global Channel Pruning for Multitask CNNs](https://mlsanity.com/paper/2303.11923/) (2023)
- [Accelerating DNN Training with Structured Data Gradient Pruning](https://mlsanity.com/paper/2202.00774/) (2022)
- [Spartan: Differentiable Sparsity via Regularized Transportation](https://mlsanity.com/paper/2205.14107/) (2022)
- [AdaSparse: Learning Adaptively Sparse Structures for Multi-Domain Click-Through Rate Prediction](https://mlsanity.com/paper/2206.13108/) (2022)
- [EfficientLLaVA:Generalizable Auto-Pruning for Large Vision-language Models](https://mlsanity.com/paper/2503.15369/) (2025)
- [Network Pruning via Resource Reallocation](https://mlsanity.com/paper/2103.01847/) (2021)
- [Toward Compact Deep Neural Networks via Energy-Aware Pruning](https://mlsanity.com/paper/2103.10858/) (2021)
- [Environmental Sound Classification on the Edge: A Pipeline for Deep Acoustic Networks on Extremely Resource-Constrained Devices](https://mlsanity.com/paper/2103.03483/) (2021)
- [Training Compact CNNs for Image Classification using Dynamic-coded Filter Fusion](https://mlsanity.com/paper/2107.06916/) (2021)

## Abstract (arXiv)

Channel pruning is an important family of methods to speed up deep model's inference. Previous filter pruning algorithms regard channel pruning and model fine-tuning as two independent steps. This paper argues that combining them into a single end-to-end trainable system will lead to better results. We propose an efficient channel selection layer, namely AutoPruner, to find less important filters automatically in a joint training manner. Our AutoPruner takes previous activation responses as an input and generates a true binary index code for pruning. Hence, all the filters corresponding to zero index values can be removed safely after training. We empirically demonstrate that the gradient information of this channel selection layer is also helpful for the whole model training. By gradually erasing several weak filters, we can prevent an excessive drop in model accuracy. Compared with previous state-of-the-art pruning algorithms (including training from scratch), AutoPruner achieves significantly better performance. Furthermore, ablation experiments show that the proposed novel mini-batch pooling and binarization operations are vital for the success of filter pruning.